zoukankan      html  css  js  c++  java
  • mysql levenshtein函数

    $word = mysql_real_escape_string($word);
    mysql_qery("SELECT `term` FROM `words` WHERE levenshtein('$word', `term`) BETWEEN 0 AND 4");

    DELIMITER $$
    CREATE FUNCTION levenshtein( s1 VARCHAR(255), s2 VARCHAR(255) )
      RETURNS INT
      DETERMINISTIC
      BEGIN
        DECLARE s1_len, s2_len, i, j, c, c_temp, cost INT;
        DECLARE s1_char CHAR;
        -- max strlen=255
        DECLARE cv0, cv1 VARBINARY(256);
        SET s1_len = CHAR_LENGTH(s1), s2_len = CHAR_LENGTH(s2), cv1 = 0x00, j = 1, i = 1, c = 0;
        IF s1 = s2 THEN
          RETURN 0;
        ELSEIF s1_len = 0 THEN
          RETURN s2_len;
        ELSEIF s2_len = 0 THEN
          RETURN s1_len;
        ELSE
          WHILE j <= s2_len DO
            SET cv1 = CONCAT(cv1, UNHEX(HEX(j))), j = j + 1;
          END WHILE;
          WHILE i <= s1_len DO
            SET s1_char = SUBSTRING(s1, i, 1), c = i, cv0 = UNHEX(HEX(i)), j = 1;
            WHILE j <= s2_len DO
              SET c = c + 1;
              IF s1_char = SUBSTRING(s2, j, 1) THEN
                SET cost = 0; ELSE SET cost = 1;
              END IF;
              SET c_temp = CONV(HEX(SUBSTRING(cv1, j, 1)), 16, 10) + cost;
              IF c > c_temp THEN SET c = c_temp; END IF;
                SET c_temp = CONV(HEX(SUBSTRING(cv1, j+1, 1)), 16, 10) + 1;
                IF c > c_temp THEN
                  SET c = c_temp;
                END IF;
                SET cv0 = CONCAT(cv0, UNHEX(HEX(c))), j = j + 1;
            END WHILE;
            SET cv1 = cv0, i = i + 1;
          END WHILE;
        END IF;
        RETURN c;
      END;$$

    CREATE FUNCTION levenshtein_ratio( s1 VARCHAR(255), s2 VARCHAR(255) )
      RETURNS INT
      DETERMINISTIC
      BEGIN
        DECLARE s1_len, s2_len, max_len INT;
        SET s1_len = LENGTH(s1), s2_len = LENGTH(s2);
        IF s1_len > s2_len THEN
          SET max_len = s1_len;
        ELSE
          SET max_len = s2_len;
        END IF;
        RETURN ROUND((1 - LEVENSHTEIN(s1, s2) / max_len) * 100);
      END; $$

    DELIMITER ;
  • 相关阅读:
    出现socket:(10107)系统调用失败
    JS面向对象基础讲解(工厂模式、构造函数模式、原型模式、混合模式、动态原型模式)
    获取滚动条距离底部的距离
    linux常用命令使用方法
    Python:一
    【C++ Primer 第15章】定义派生类拷贝构造函数、赋值运算符
    【【C++ Primer 第15章】 虚析构函数
    ubuntu基本用法
    深度优先搜索(DFS)和广度优先搜索(BFS)
    【C++ Primer 第7章】定义抽象数据类型
  • 原文地址:https://www.cnblogs.com/justinsun/p/3510852.html
Copyright © 2011-2022 走看看